Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986460
Rakshitha R, S. S
Road transportation system facilitates the movement of people, goods and contributes to the national economy. This pavement network keeps on growing as years pass on. The failure of pavement may be due to heavy traffic, sunlight exposure, the seasonal changes causes unequal expansion and contraction of the surface, water intrusion and quality of construction material. Hence there is a high demand for effective pavement maintenance and rehabilitation in early stages. A lot of research is actively being conducted on detection and assessment of pavement distress. The manual approach depends on expert knowledge, consumes lot of time and it lacks the objectivity for quantification, then the automated distress detection using 3D laser technology uses hardware equipment which requires huge budget investment, hence AI based pavement distress detection and quantification methods are proposed as replacement. This paper presents a review of papers from the repositories like Google Scholar, Scopus, MDPI, ASCE (American Society of Civil Engineers) library, Hindawi of past eight years based on image processing and deep learning techniques that performs the task of detection and quantification of distress type, and advantages and disadvantages of the existing system are outlined and accounts for the interdisciplinary research to provide information for civil and the computer science enthusiast to know about the research challenges in this field needed for future research.
{"title":"A Comprehensive Review on Asphalt Pavement Distress Detection and Assessment based on Artificial Intelligence","authors":"Rakshitha R, S. S","doi":"10.1109/UPCON56432.2022.9986460","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986460","url":null,"abstract":"Road transportation system facilitates the movement of people, goods and contributes to the national economy. This pavement network keeps on growing as years pass on. The failure of pavement may be due to heavy traffic, sunlight exposure, the seasonal changes causes unequal expansion and contraction of the surface, water intrusion and quality of construction material. Hence there is a high demand for effective pavement maintenance and rehabilitation in early stages. A lot of research is actively being conducted on detection and assessment of pavement distress. The manual approach depends on expert knowledge, consumes lot of time and it lacks the objectivity for quantification, then the automated distress detection using 3D laser technology uses hardware equipment which requires huge budget investment, hence AI based pavement distress detection and quantification methods are proposed as replacement. This paper presents a review of papers from the repositories like Google Scholar, Scopus, MDPI, ASCE (American Society of Civil Engineers) library, Hindawi of past eight years based on image processing and deep learning techniques that performs the task of detection and quantification of distress type, and advantages and disadvantages of the existing system are outlined and accounts for the interdisciplinary research to provide information for civil and the computer science enthusiast to know about the research challenges in this field needed for future research.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127400358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986417
Parul Saini, K. Kumar, Shamal Kashid, Abhishek Dhiman, Alok Negi
In recent years, the significant research area in the domain of multimedia security is image information security. This can be provided by converting it into a secret code through the process of encryption or hiding its true significance or a combination of both. It is required in many domains like defence, military, banking, education, etc, to keep these sensitive images from being hacked or destroyed. In this paper, BEMSS, an (n,n) multi-secret image encryption with a secret sharing scheme is proposed using blockwise encryption. In the proposed technique two-level encryption, modulo and inter blockwise encryption, are performed to the n secret images, and a two-level share generation process is performed to the encrypted images. BEMSS recovers n lossless the secret images by modulo and blockwise decryption process. Experimental results obtained show the effectiveness of the proposed BEMSS which provide a computationally efficient security scheme.
{"title":"BEMSS- Blockwise Encryption based Multi Secret Sharing scheme for Securing Visual Content","authors":"Parul Saini, K. Kumar, Shamal Kashid, Abhishek Dhiman, Alok Negi","doi":"10.1109/UPCON56432.2022.9986417","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986417","url":null,"abstract":"In recent years, the significant research area in the domain of multimedia security is image information security. This can be provided by converting it into a secret code through the process of encryption or hiding its true significance or a combination of both. It is required in many domains like defence, military, banking, education, etc, to keep these sensitive images from being hacked or destroyed. In this paper, BEMSS, an (n,n) multi-secret image encryption with a secret sharing scheme is proposed using blockwise encryption. In the proposed technique two-level encryption, modulo and inter blockwise encryption, are performed to the n secret images, and a two-level share generation process is performed to the encrypted images. BEMSS recovers n lossless the secret images by modulo and blockwise decryption process. Experimental results obtained show the effectiveness of the proposed BEMSS which provide a computationally efficient security scheme.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128893094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986424
T. Kumar, Ramesh Kumar Bhukya
Speech recognition refers to the technology that enables machines to recognize persons using their speech utterances. An automatic speaker verification (ASV) is included in one of the challenging task in speech community. The ASV system works based on the speaker recognition claimed against the model. In this paper, the system works as a text-independent speaker verification (TISV) and is outlined to verify the speaker using his/her voice samples. We followed two approaches, first approach is Gaussian Mixture Model (GMM) method is used to create speaker modeling and the second approach are GMMs created from training dataset, with Universal Background Model (UBM) used for adaptation of the dataset, well known approach for speaker verification (SV). GMM-UBMs are designed as well classifier for decision making. In both the approaches, the training is performed by the Expectation Maximization (EM) and Maximum A Posteriori (MAP) adaptation for better models respectively. The NIST 2003 database is evaluated using adapted GMM-UBM following NIST 2003 speaker recognition evaluation protocol and the relative performance improvement in the SV system using GMM and GMM-UBM in terms of EER are 9.43% and 8.88%.
{"title":"Mel Spectrogram Based Automatic Speaker Verification Using GMM-UBM","authors":"T. Kumar, Ramesh Kumar Bhukya","doi":"10.1109/UPCON56432.2022.9986424","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986424","url":null,"abstract":"Speech recognition refers to the technology that enables machines to recognize persons using their speech utterances. An automatic speaker verification (ASV) is included in one of the challenging task in speech community. The ASV system works based on the speaker recognition claimed against the model. In this paper, the system works as a text-independent speaker verification (TISV) and is outlined to verify the speaker using his/her voice samples. We followed two approaches, first approach is Gaussian Mixture Model (GMM) method is used to create speaker modeling and the second approach are GMMs created from training dataset, with Universal Background Model (UBM) used for adaptation of the dataset, well known approach for speaker verification (SV). GMM-UBMs are designed as well classifier for decision making. In both the approaches, the training is performed by the Expectation Maximization (EM) and Maximum A Posteriori (MAP) adaptation for better models respectively. The NIST 2003 database is evaluated using adapted GMM-UBM following NIST 2003 speaker recognition evaluation protocol and the relative performance improvement in the SV system using GMM and GMM-UBM in terms of EER are 9.43% and 8.88%.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"72 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132078877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986366
Nalini Pusarla, Ashutosh Kumar Singh, S. Tripathi
Emotion is very essential natural feeling of humans. Emotion recognition is often used in brain-computer interface devices to assist impaired people. Electroencephalogram (EEG) signal is essential for identifying emotional states since it reacts instantly to every variation in the individual's brain. In this work, the usefulness of the tunable-Q wavelet transform (TQWT) for classifying various emotions in EEG signals is studied. TQWT breaks the EEG signals into sub-bands and extracts statistical momemts from the sub-bands. The extracted moments are features which are fed to classifier named extreme learning machine, which classifies different emotions. In comparison to other existing approaches, the experimental results of the proposed technique acheived improved emotion recognition performance on open-source datasets, SEED, SEED-IV, and DEAP. The maximum accuracy obtained with the proposed emotion recognition system is 95.2%, 95%, and 93.8% using SEED, SEED-IV, and DEAP databases, respectively, which is higher compared to the state-of-art methods.
{"title":"Automatic EEG Based Emotion Recognition Using Extreme Learning Machine","authors":"Nalini Pusarla, Ashutosh Kumar Singh, S. Tripathi","doi":"10.1109/UPCON56432.2022.9986366","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986366","url":null,"abstract":"Emotion is very essential natural feeling of humans. Emotion recognition is often used in brain-computer interface devices to assist impaired people. Electroencephalogram (EEG) signal is essential for identifying emotional states since it reacts instantly to every variation in the individual's brain. In this work, the usefulness of the tunable-Q wavelet transform (TQWT) for classifying various emotions in EEG signals is studied. TQWT breaks the EEG signals into sub-bands and extracts statistical momemts from the sub-bands. The extracted moments are features which are fed to classifier named extreme learning machine, which classifies different emotions. In comparison to other existing approaches, the experimental results of the proposed technique acheived improved emotion recognition performance on open-source datasets, SEED, SEED-IV, and DEAP. The maximum accuracy obtained with the proposed emotion recognition system is 95.2%, 95%, and 93.8% using SEED, SEED-IV, and DEAP databases, respectively, which is higher compared to the state-of-art methods.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125573339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986386
Kailash Kushwaha, R. Singh
This paper describes the design of a power supply intended for a traveling wave tube (TWT) power supply. For the faithful operation of the TWT amplifier, constant DC voltages are required for the operation of the collector supply, heater supply, helix supply, and control grid. In this work, the mains interface circuit for a TWT amplifier is designed and simulated using Proteus 8.9. For the removal of the ripples in the main power supply, a two-inductor based choke filter is connected in series to get ripple-free signal. The mains interface power supply generates three DC output voltages typically 300V, 150V, and +12V.
{"title":"Mains Interface Circuit Design for Traveling Wave Tube Amplifier","authors":"Kailash Kushwaha, R. Singh","doi":"10.1109/UPCON56432.2022.9986386","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986386","url":null,"abstract":"This paper describes the design of a power supply intended for a traveling wave tube (TWT) power supply. For the faithful operation of the TWT amplifier, constant DC voltages are required for the operation of the collector supply, heater supply, helix supply, and control grid. In this work, the mains interface circuit for a TWT amplifier is designed and simulated using Proteus 8.9. For the removal of the ripples in the main power supply, a two-inductor based choke filter is connected in series to get ripple-free signal. The mains interface power supply generates three DC output voltages typically 300V, 150V, and +12V.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114179803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986462
Indradeo Pratap Bharti, Prince Kumar, N. Singh, O. Gupta, N. Choudhary, Ashutosh Kumar Singh
Islanding is a well-known phenomenon in Distributed Generation (DG) in which the microgrid continues to provide power to an isolated load area even after it is disconnected from the utility grid. Fast detection of islanding is very important to maintain stability in voltage and frequency, restrict the disturbances within permissible limits, and prevent faults and cascade tripping in the grid. In case of delayed islanding detection, the system may have increased harmonics, distorted voltage profile during the transition, faults, and service interruption during critical loads. The main disadvantage of passive detection approaches is their large non-detection zone. Due to external signal injection at a common coupling point, active islanding reduces power quality and system performance. The suggested passive islanding detection approach is based on measuring the negative sequence voltage rate of change (ROCONSV) at the point of common connection (PCC). The negative sequence voltage is calculated using symmetrical component transformation and the derivative is then compared to predefined threshold values. Based on the system decision, the islanding trip signal is released for the circuit breaker at the microgrid. The proposed method is simple, reliable, and fast without the use of any external signal injection and power quality degradation.
{"title":"A Passive Technique for Detecting Islanding Using Voltage Sequence Component","authors":"Indradeo Pratap Bharti, Prince Kumar, N. Singh, O. Gupta, N. Choudhary, Ashutosh Kumar Singh","doi":"10.1109/UPCON56432.2022.9986462","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986462","url":null,"abstract":"Islanding is a well-known phenomenon in Distributed Generation (DG) in which the microgrid continues to provide power to an isolated load area even after it is disconnected from the utility grid. Fast detection of islanding is very important to maintain stability in voltage and frequency, restrict the disturbances within permissible limits, and prevent faults and cascade tripping in the grid. In case of delayed islanding detection, the system may have increased harmonics, distorted voltage profile during the transition, faults, and service interruption during critical loads. The main disadvantage of passive detection approaches is their large non-detection zone. Due to external signal injection at a common coupling point, active islanding reduces power quality and system performance. The suggested passive islanding detection approach is based on measuring the negative sequence voltage rate of change (ROCONSV) at the point of common connection (PCC). The negative sequence voltage is calculated using symmetrical component transformation and the derivative is then compared to predefined threshold values. Based on the system decision, the islanding trip signal is released for the circuit breaker at the microgrid. The proposed method is simple, reliable, and fast without the use of any external signal injection and power quality degradation.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114205701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986444
M. K. Maurya, Mandeep Kumar, Manish Kumar
The study of sound event detection (SED) in environmental environments has gained popularity recently. However, significant logistical and privacy concerns exist because huge amounts of (private) home or urban audio data are needed. Federated learning (FL), which effectively distributes these duties, is a viable way to use enormous amounts of data without raising privacy issues. Although FL has recently gained much attention, only a few studies have been done on FL for SED. In this paper, we attempted FL for SED to fill this gap and encourage further study. This paper demonstrated the experiments on the URBAN and MNIST datasets to better understand the impact of data heterogeneity, optimizer, client participation, and communication round. Additionally, we run baseline outcomes for deep neural network designs on the datasets in an FL context. The CNN-M model is used for training and testing purposes; two datasets, namely URBAN and MNIST audio datasets, are used.
{"title":"Sound Event Detection using Federated Learning","authors":"M. K. Maurya, Mandeep Kumar, Manish Kumar","doi":"10.1109/UPCON56432.2022.9986444","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986444","url":null,"abstract":"The study of sound event detection (SED) in environmental environments has gained popularity recently. However, significant logistical and privacy concerns exist because huge amounts of (private) home or urban audio data are needed. Federated learning (FL), which effectively distributes these duties, is a viable way to use enormous amounts of data without raising privacy issues. Although FL has recently gained much attention, only a few studies have been done on FL for SED. In this paper, we attempted FL for SED to fill this gap and encourage further study. This paper demonstrated the experiments on the URBAN and MNIST datasets to better understand the impact of data heterogeneity, optimizer, client participation, and communication round. Additionally, we run baseline outcomes for deep neural network designs on the datasets in an FL context. The CNN-M model is used for training and testing purposes; two datasets, namely URBAN and MNIST audio datasets, are used.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"326-327 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121095872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986431
P. Kumawat, Utkarsh, Aditya Chikhale, Ramesh Kumar Bhukya
The COVID-19 pandemic bestows global challenges surpassing boundaries of country, religion race, and economy. Testing of COVID-19 patients conditions are remains a challenging task due to the lack of adequate medical supplies, well-trained personnel and conducting reverse transcription polymerase chain reaction (RT-PCR) testing is expensive, long-drown-out process violates social distancing. In this direction, we used microbiologically confirmed COVID-19 dataset based on cough recordings from Coswara dataset. The Coswara dataset is also one of the open challenge dataset for researchers to investigate sound recordings of the Coswara dataset, collected from COVID-19 infected and non-COVID-19 individuals, for classification between Positive and Negative detection. These COVID-19 recordings were collected from multiple countries, through the provided crowd-sourcing website. Here, our work mainly focuses on cough sound based recordings. The dataset is released open access. We developed an acoustic biosignature feature extractors to screen for potential problems from cough recordings, and provide personalized advice to a particular patient's state to monitor his suitable condition in real-time. In our work, cough sound recordings are converted into Mel Frequency Cepstral Coefficients (MFCCs) and passed through a Gaussian Mixture Model (GMM) based pattern recognition, decision making based on a binary pre-screening diagnostic. When validated with infected and non-infected patients, for a two-class classification, using a Coswara dataset. The GMM is applied for developing a model for detection of biomarker based detection and achieves COVID-19 and non-COVID-19 patients accuracy of 73.22% based on the Coswara dataset and also compared with existing classifiers.
{"title":"COVID-19 Detection From Audio Signals Using LR-MLP-RF-GMM Classifiers","authors":"P. Kumawat, Utkarsh, Aditya Chikhale, Ramesh Kumar Bhukya","doi":"10.1109/UPCON56432.2022.9986431","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986431","url":null,"abstract":"The COVID-19 pandemic bestows global challenges surpassing boundaries of country, religion race, and economy. Testing of COVID-19 patients conditions are remains a challenging task due to the lack of adequate medical supplies, well-trained personnel and conducting reverse transcription polymerase chain reaction (RT-PCR) testing is expensive, long-drown-out process violates social distancing. In this direction, we used microbiologically confirmed COVID-19 dataset based on cough recordings from Coswara dataset. The Coswara dataset is also one of the open challenge dataset for researchers to investigate sound recordings of the Coswara dataset, collected from COVID-19 infected and non-COVID-19 individuals, for classification between Positive and Negative detection. These COVID-19 recordings were collected from multiple countries, through the provided crowd-sourcing website. Here, our work mainly focuses on cough sound based recordings. The dataset is released open access. We developed an acoustic biosignature feature extractors to screen for potential problems from cough recordings, and provide personalized advice to a particular patient's state to monitor his suitable condition in real-time. In our work, cough sound recordings are converted into Mel Frequency Cepstral Coefficients (MFCCs) and passed through a Gaussian Mixture Model (GMM) based pattern recognition, decision making based on a binary pre-screening diagnostic. When validated with infected and non-infected patients, for a two-class classification, using a Coswara dataset. The GMM is applied for developing a model for detection of biomarker based detection and achieves COVID-19 and non-COVID-19 patients accuracy of 73.22% based on the Coswara dataset and also compared with existing classifiers.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115273243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986364
Uday Singh, Shailendra Shukla, M. M. Gore
Autism Spectrum Disorder (ASD) is one of the most common acute neurodevelopmental disorders. It is associated with the development of the brain. ASD severely affects a child's physical and mental health. ASD detection at an early age is challenging as its symptoms come after two years. Each ASD patient has a different set of symptoms (features). In recent years, machine learning has offered a new potential solution for the detection of Autism. The effectiveness of the machine learning models depends on the dataset's features. This paper proposes a feature selection algorithm (which is based on feature correlation and ranking) for early ASD detection on the clinical ASD dataset. The performance of the feature selection algorithm is compared with different machine learning algorithms (LR, GBC, AdaBoost, and DT). The result shows that 5 out of the 30 features with a Logistic Regression model are sufficient to detect Autism with 98.18% accuracy, 98.16% sensitivity, and 98.16% precision. The result also shows that the Gradient Boost achieves 98.18% accuracy with 5 features, and the AdaBoost achieves 97.10% accuracy with 5 features.
{"title":"An Improved Feature Selection Algorithm for Autism Detection","authors":"Uday Singh, Shailendra Shukla, M. M. Gore","doi":"10.1109/UPCON56432.2022.9986364","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986364","url":null,"abstract":"Autism Spectrum Disorder (ASD) is one of the most common acute neurodevelopmental disorders. It is associated with the development of the brain. ASD severely affects a child's physical and mental health. ASD detection at an early age is challenging as its symptoms come after two years. Each ASD patient has a different set of symptoms (features). In recent years, machine learning has offered a new potential solution for the detection of Autism. The effectiveness of the machine learning models depends on the dataset's features. This paper proposes a feature selection algorithm (which is based on feature correlation and ranking) for early ASD detection on the clinical ASD dataset. The performance of the feature selection algorithm is compared with different machine learning algorithms (LR, GBC, AdaBoost, and DT). The result shows that 5 out of the 30 features with a Logistic Regression model are sufficient to detect Autism with 98.18% accuracy, 98.16% sensitivity, and 98.16% precision. The result also shows that the Gradient Boost achieves 98.18% accuracy with 5 features, and the AdaBoost achieves 97.10% accuracy with 5 features.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121392290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/UPCON56432.2022.9986432
Priyam Bajpai, R. Sanodiya
This paper addresses the problem of unsupervised domain adaptation in a setup where a single source is not sufficient for training the model. In this situation, a hybrid, multi-source driven training dataset is used. This calls for the need of an effective method to align the geometrically quasi-related source domains which would help prepare a better ground for aligning the unlabeled target dataset. We propose a robust framework that helps in better domain adaptation by reducing the probabilistic and subspace shift between the domains without compromising with their distributional information, and diminishing the distance of the between-class and within-class scatter of the domains collectively. The algorithm generates pseudo-labels after each iteration to update its objective function, thus helping it to perform better than conventional methods. The proposed framework tackles non-linear divergence by projecting the features into the kernel space. Computational experiments and their analysis show that the proposed algorithm performs better than other state-of-the-art domain adaptation methods on various visual recognition tasks.
{"title":"A Unified Framework for Covariance Adaptation with Multiple Source Domains","authors":"Priyam Bajpai, R. Sanodiya","doi":"10.1109/UPCON56432.2022.9986432","DOIUrl":"https://doi.org/10.1109/UPCON56432.2022.9986432","url":null,"abstract":"This paper addresses the problem of unsupervised domain adaptation in a setup where a single source is not sufficient for training the model. In this situation, a hybrid, multi-source driven training dataset is used. This calls for the need of an effective method to align the geometrically quasi-related source domains which would help prepare a better ground for aligning the unlabeled target dataset. We propose a robust framework that helps in better domain adaptation by reducing the probabilistic and subspace shift between the domains without compromising with their distributional information, and diminishing the distance of the between-class and within-class scatter of the domains collectively. The algorithm generates pseudo-labels after each iteration to update its objective function, thus helping it to perform better than conventional methods. The proposed framework tackles non-linear divergence by projecting the features into the kernel space. Computational experiments and their analysis show that the proposed algorithm performs better than other state-of-the-art domain adaptation methods on various visual recognition tasks.","PeriodicalId":185782,"journal":{"name":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114262602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：